© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 2246
    Prev
    Next
    INDEX
    Explanations

    sports league and tournament events

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åIJĦè¡ĮåIJĦä¸ļ
    -0.24
     *)((
    -0.24
    å¾ĹäºĨ
    -0.24
    åĩºå¢ĥ
    -0.24
    å¼ĢåıijèĢħ
    -0.23
    otten
    -0.23
    åĽłä¸ºæĪij
    -0.22
    acher
    -0.22
    æĺ¯ä¸Ģ座
    -0.22
    éķľåŃIJ
    -0.22
    POSITIVE LOGITS
    缸éģĩ
    0.28
    cross
    0.27
     prelim
    0.26
    /lic
    0.24
     preliminary
    0.24
    交åıī
    0.23
     cross
    0.23
     ens
    0.23
    /*@
    0.23
     prere
    0.22
    Activations Density 0.057%

    No Known Activations